MCDC Legacy
Supporting Instruction with Real Data Problems
Big Picture/Overview
Where does model evaluation and selection come up during an introductory machine learning course?
Early on, maybe first day — How do we know if a model is any good?
During model building/training — How to pick the “best” model?
Discussion of final model — How will the final model preform?
Basic structure
Who is working on it, where is data coming from, where it will be located
Examples
How do we know if a model is any good?
